Labsco
HrRodan logo

Secure Agent Workspace

★ 1

from HrRodan

A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.

🔥🔥🔥🔥✓ VerifiedAccount requiredNeeds API keys
#automation#devops#git#security#monitoring

🛡️ Agent Workspace MCP Server

CI License: MIT Python 3.14+

A unified Model Context Protocol (MCP) server providing a highly secure, containerized workspace for Large Language Models (LLMs). It acts as an isolated "agentic playground" where agents can autonomously code, test, and debug without risking the host machine.

✨ Features

  • 🏗️ Full Project Lifecycle: Bootstrap projects with uv init, manage dependencies with uv add, and execute via uv run.
  • 🐚 Secure Bash Access: Execute shell commands with mandatory timeouts and merged output streams.
  • 🚀 Token-Optimized Output: Integrates RTK (Rust Token Killer) to automatically filter and compress run_bash outputs (like ls, git, and test runners), saving 60-90% of LLM context tokens.
  • 📂 Robust Filesystem: Path-traversal protected operations for reading, writing, and searching the workspace.
  • 🛡️ Multi-Layer Security: Non-root execution, dropped capabilities, resource limits, and a read-only root filesystem.
  • ⚡ Precision Editing: Advanced search_and_replace with fuzzy whitespace matching, indentation preservation, dry-run support, and syntax validation for Python, JSON, JSONL, TOML, and YAML.
  • 📊 Real-time Observability: Direct logging to MCP client UI and persistent rotating audit logs.

🏗️ Architecture

flowchart TD
    Client["MCP Client (Claude / Cursor)"] -- "stdio (JSON-RPC)" --> FastMCP["FastMCP Server"]

    subgraph Sandbox ["Docker Sandbox Container (mcpuser)"]
        direction TB
        
        FastMCP -. "Intercepts accidental prints" .-> StdioGuard["StdoutRedirector"]
        FastMCP -. "Application Logs" .-> Logger["Dual Logger (stderr & .mcp/server.log)"]
        
        FastMCP -- "Tool Calls" --> SecurityGuard["Security & Path Validator"]
        
        subgraph Toolset ["Tool Modules"]
            direction TB
            SecurityGuard --> FSTools["Filesystem (read, write, list, search)"]
            SecurityGuard --> EditTools["Editing (search_and_replace)"]
            SecurityGuard --> ExecTools["Execution (run_bash)"]
        end

        EditTools -- "AST Verification" --> Validator["Syntax Validations (Python, JSON, JSONL, TOML, YAML)"]
        ExecTools -- "Process Group (Timeout=60s)" --> Shell["/bin/sh Subprocess"]
        Shell -- "Package Mgt & Checks" --> UV["uv Environment / Ruff"]
        
        FSTools -- "Secure I/O" --> Workspace["/workspace Directory"]
        EditTools -- "Atomic Writes" --> Workspace
        Shell -- "Executes within" --> Workspace
    end

    Workspace <--"Volume Mount"--> HostFS["User Host Filesystem"]

🛠️ Tool Reference

ToolDescription
read_fileRead text files with optional offset and limit (default: 100 lines).
write_fileCreate files with syntax validation and a 5MB size guard. Refuses to overwrite existing files by default (create_only=True).
list_directoryList contents with [F]ile and [D]irectory prefixes.
search_workspaceFind files by glob pattern with support for exclude_patterns.
run_bashExecute shell commands in /workspace with a 60s timeout. Automatically optimized via RTK to reduce token usage.
search_and_replaceMulti-edit tool with fuzzy whitespace matching, indentation preservation, dry-run mode, and syntax validation (Python, JSON, JSONL, TOML, YAML).

🛡️ Security & Architecture Model

This server employs a defense-in-depth strategy, explicitly separating strict security boundaries from developer experience and operational reliability features.

🔒 Core Security Features

These features are designed to protect the host system and enforce strict isolation boundaries.

  • Kernel Hardening: All Linux capabilities are dropped (--cap-drop=ALL), neutralizing privilege escalation vectors.
  • Immutable Server Code: The /app directory containing the server source and its virtual environment is owned by root and read-only for the mcpuser. This prevents the server from modifying itself or being tampered with via run_bash.
  • Privilege Lockdown: Enforces no-new-privileges:true to prevent any process from gaining elevated rights.
  • Immutable System Core: The container's root filesystem is mounted entirely read-only, providing a second layer of defense against OS-level tampering.
  • Resource Quotas: Hard limitations on CPU, Memory, and PIDs mitigate denial-of-service (DoS) attempts like fork-bombs and host exhaustion.
  • Strict Boundary Enforcement: A robust path validator comprehensively blocks all path traversal attacks outside the designated /workspace.
  • Process & Resource Control: Mandatory command timeouts (default 60s) and strict process group isolation ensure runaway or malicious processes are killed.
  • Memory-Overload Protection: Hard limits on file reads (1MB) and command outputs (50KB) prevent memory exhaustion.
  • Information Leakage Prevention: Internal stack traces and system paths are suppressed and sanitized from tool outputs.

🛠️ Developer Experience & Convenience

Features focused on seamless integration, usability, and reducing friction during agentic workflows.

  • Host-Aligned Non-Root Identity: Runs as mcpuser with UID/GID customizable at build time, eliminating tedious file permission conflicts on host volume mounts.
  • Automatic Token Optimization: Shell commands executed via run_bash are transparently rewritten through RTK to provide ultra-compact, LLM-friendly output without altering underlying command behavior.
  • Intelligent Search Exclusions: High-noise or sensitive directories (.git, .venv) are automatically ignored to keep context windows lean and relevant.
  • Ephemeral Workspaces: Containers are strictly ephemeral (--rm), guaranteeing a clean, predictable slate for every new session without state leaking across connections.
  • Standardized Discovery: Complies with the OCI Image Specification for standardized container ecosystem integration and transparent auditing.

⚙️ Reliability & Safety Mechanisms

Features ensuring the structural integrity of the workspace and providing observability.

  • Pre-Write Syntax Validation: Both write_file and search_and_replace perform in-memory syntax validation for Python, JSON, JSONL, TOML, and YAML before persisting changes, preventing broken code states.
  • Fail-Safe Writing: write_file blocks accidental overwrites of existing files by default and enforces a 5MB size guard to prevent workspace flooding.
  • Atomic File Operations: Edits utilize temp-and-move logic to guarantee file integrity and prevent corruption, even during unexpected interruptions or crashes.
  • Transparent Observability: All tool invocations and state changes are streamed in real-time to the MCP client UI for immediate operator oversight.

🌐 Network Isolation (Optional)

By default, the container has full network access via Docker's bridge network. For maximum isolation, you can completely disable the network stack using --network none:

docker run -i --rm --init \
  --network none \
  --memory=2g --cpus=2.0 --pids-limit=256 \
  --cap-drop=ALL --security-opt=no-new-privileges:true \
  --read-only \
  --tmpfs /tmp:size=64m \
  --tmpfs /home/mcpuser/.cache:size=512m \
  --user 1000:1000 \
  -v /path/to/your/projects:/workspace \
  ghcr.io/hrrodan/agent-workspace-mcp:latest

This creates a fully air-gapped sandbox — only the loopback interface exists inside the container. All outbound connections (curl, DNS, uv add, etc.) will fail immediately, eliminating data exfiltration and lateral movement risks entirely.

[!NOTE] With --network none, the agent cannot install packages at runtime. All dependencies must be pre-installed in a custom image or pre-populated in the mounted workspace volume.

🤝 Contributing

  1. Install Dev Dependencies: uv sync
  2. Run Linting: uv run ruff check .
  3. Run Unit Tests: uv run pytest tests/ --ignore=tests/integration/
  4. Run Integration Tests: Set OPENROUTER_API_KEY and run uv run pytest tests/integration/

© 2026 HrRodan. Licensed under MIT.